© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1391
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to classification and identification in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    0.9%
    876
    +0.10
    0.4%
    1226
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1226
    +0.26
    0.04
    1952
    +0.10
    0.04
    464
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.61
    HasOne
    -0.81
     and
    -0.80
    HasIndex
    -0.79
     do
    -0.76
     at
    -0.75
     could
    -0.73
     during
    -0.73
     for
    -0.72
     did
    -0.71
    POSITIVE LOGITS
     increa
    2.64
     affor
    2.54
     fta
    2.52
     aen
    2.52
     effe
    2.51
     stockholm
    2.50
     maneu
    2.43
     inev
    2.41
     ftu
    2.41
     thut
    2.40
    Activations Density 0.317%

    No Known Activations